TopoPrimer: The Missing Topological Context in Forecasting Models Paper • 2605.15035 • Published 16 days ago • 3
Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why Paper • 2605.10889 • Published 19 days ago • 5
A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models Paper • 2605.08513 • Published 22 days ago • 16
BalCapRL: A Balanced Framework for RL-Based MLLM Image Captioning Paper • 2605.07394 • Published 22 days ago • 5
Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation Paper • 2605.07924 • Published 22 days ago • 1
STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation Paper • 2605.08029 • Published 22 days ago • 12
Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling Paper • 2604.27039 • Published Apr 29 • 25
MobileCLIP2 Collection MobileCLIP2: Mobile-friendly image-text models with SOTA zero-shot capabilities trained on DFNDR-2B • 30 items • Updated Apr 23 • 62